From f11b97ae483302a37b04d5cb3bf7af4a13121b20 Mon Sep 17 00:00:00 2001
From: PENG Bo <33809201+BlinkDL@users.noreply.github.com>
Date: Sat, 26 Mar 2022 23:26:06 +0800
Subject: [PATCH] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index a37dc4a..cbe1eb0 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,8 @@ You only need x_t, a_t, b_t of position t to compute the vectors for position t+
 
 Hence it can be 100x faster than GPT, and 100x more VRAM friendly.
 
+See the release for a 27M params model on enwik8 with 1.65 dev perplexity (0.72 BPC).
+
 ## How it works
 
 The a b c d factors work together to build a time-decay curve: X, 1, W, W^2, W^3, ...